© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1676
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement organizations and their operational details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after "of" relating to organizations/authorities

    np_acts-logits-general · gemini-2.0-flash

    chief of police organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ômico
    -0.60
     Şi
    -0.56
     sostuvo
    -0.49
    Şi
    -0.49
     Fayette
    -0.48
     Estadual
    -0.47
     realtor
    -0.46
     şi
    -0.46
    Nbr
    -0.46
     sólo
    -0.44
    POSITIVE LOGITS
    abestanden
    0.89
    WriteTagHelper
    0.76
    MigrationBuilder
    0.71
    -£
    0.69
     استنادى
    0.67
    cetamol
    0.66
     fortn
    0.65
     Forumite
    0.65
    RetentionPolicy
    0.64
    Prezzo
    0.64
    Activations Density 0.383%

    No Known Activations